Collaborative Research: SAI-R: Dynamical Coupling of Physical and Social Infrastructures: Evaluating the Impacts of Social Capital on Access to Safe Well Water

合作研究：SAI-R：物理和社会基础设施的动态耦合：评估社会资本对获得安全井水的影响

• 批准号: 2228534
• 负责人: Jundong Li
• 金额: $ 25万
• 依托单位: University of Virginia Main Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-15 至 2025-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2228534&HistoricalAwards=false
• 关键词: Collaborative; Research; SAI; Dynamical; Coupling

Strengthening American Infrastructure (SAI) is an NSF Program seeking to stimulate human-centered fundamental and potentially transformative research that strengthens America’s infrastructure. Effective infrastructure provides a strong foundation for socioeconomic vitality and broad quality of life improvement. Strong, reliable, and effective infrastructure spurs private-sector innovation, grows the economy, creates jobs, makes public-sector service provision more efficient, strengthens communities, promotes equal opportunity, protects the natural environment, enhances national security, and fuels American leadership. To achieve these goals requires expertise from across the science and engineering disciplines. SAI focuses on how knowledge of human reasoning and decision-making, governance, and social and cultural processes enables the building and maintenance of effective infrastructure that improves lives and society and builds on advances in technology and engineering.Access to a safe supply of drinking water is essential for the health and welfare of all people. In many places, private wells are the primary source of water for residents. This SAI research project examines the availability of potable drinking water to individuals and households in settings where private wells are the predominant source of water for residents. Maintaining a safe supply of drinking water may be particularly challenging for residents who lack broad access to social support, as reflected in geographic connections to other communities. This support may be especially important in the aftermath of natural disasters and related hazards that disrupt water supplies. This project uses data on the mobility of cell phone users to characterize the social assistance that residents call upon. Methods are used to account for unequal representation of different groups in such datasets. The analysis considers other variables that may cause variation in water quality, such as demographic and socioeconomic factors. Water quality is evaluated with samples of private wells and surveys with owners. The project places high priority on sharing important findings with stakeholders, including extension services and health departments. The project also contributes to middle and high school curricula that will be shared and used in diverse public school settings.Multiple, complementary datasets are leveraged to examine the ways in which advantageous positions in social networks may contribute to better water quality in private wells, particularly in geographic settings that have been impacted by recent flooding. Social networks are constructed from data on the mobility of cellular phone users, and new algorithmic approaches are developed to address the biases that typify these data. Upon constructing these networks, measures of positions in social networks are used to predict variation in the contamination of private wells. The algorithmic approaches developed for graph neural network analysis will have broader potential applications in similar research that seeks to account for biases in the representativeness of large archival datasets, including biases that disadvantage vulnerable populations. The project involves multiple students, contributing to the training and education of early-career scientists.This award is supported by the Directorate for Social, Behavioral, and Economic (SBE) Sciences and the Directorate for Geosciences.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

加强美国基础设施（SAI）是美国国家科学基金会的一个项目，旨在促进以人为本的基础研究和潜在的变革性研究，以加强美国的基础设施。有效的基础设施为社会经济活力和广泛的生活质量改善提供了坚实的基础。强大、可靠和有效的基础设施刺激私营部门的创新，发展经济，创造就业机会，使公共部门提供的服务更有效率，加强社区，促进机会平等，保护自然环境，加强国家安全，并推动美国的领导地位。为了实现这些目标，需要来自科学和工程学科的专业知识。SAI侧重于人类推理和决策、治理以及社会和文化过程的知识如何使有效的基础设施的建设和维护能够改善生活和社会，并以技术和工程的进步为基础。获得安全的饮用水供应对所有人的健康和福利至关重要。在许多地方，私人水井是居民的主要水源。这个SAI研究项目调查了在私人水井是居民主要水源的环境中，个人和家庭的饮用水供应情况。对于缺乏广泛获得社会支持的居民来说，维持安全的饮用水供应可能尤其具有挑战性，这反映在与其他社区的地理联系上。在自然灾害和有关破坏供水的危险发生后，这种支助可能特别重要。该项目使用手机用户的移动数据来描述居民所要求的社会援助。方法用于解释这些数据集中不同组的不平等表示。该分析考虑了其他可能导致水质变化的变量，如人口和社会经济因素。我们抽取私人水井样本，并与业主进行调查，以评估水质。该项目高度重视与包括推广服务和卫生部门在内的利益攸关方分享重要发现。该项目还为初中和高中课程做出了贡献，这些课程将在不同的公立学校环境中共享和使用。利用多个互补数据集来检查社交网络中的优势位置可能有助于改善私人水井水质的方式，特别是在受最近洪水影响的地理环境中。社交网络是从移动电话用户的移动性数据中构建的，并且开发了新的算法方法来解决这些数据的偏见。在构建这些网络后，社会网络中的位置测量被用来预测私人井污染的变化。为图神经网络分析开发的算法方法将在类似的研究中具有更广泛的潜在应用，这些研究旨在解释大型档案数据集代表性中的偏差，包括对弱势群体不利的偏差。该项目涉及多个学生，为早期职业科学家的培训和教育做出了贡献。该奖项由社会、行为和经济（SBE）科学理事会和地球科学理事会支持。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Federated Few-shot Learning

• DOI: 10.1145/3580305.3599347
• 发表时间: 2023-06
• 期刊: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Song Wang;Xingbo Fu;Kaize Ding;Chen Chen-Chen;Huiyuan Chen;Jundong Li

Fairness in Graph Mining: A Survey

• DOI: 10.1109/tkde.2023.3265598
• 发表时间: 2022-04
• 期刊: IEEE Transactions on Knowledge and Data Engineering
• 影响因子: 8.9
• 作者: Yushun Dong;Jing Ma;Song Wang;Chen Chen-Chen;Jundong Li

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

通过训练节点归因解释图神经网络中的不公平性

• DOI: 10.1609/aaai.v37i6.25905
• 发表时间: 2023
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Dong, Yushun;Wang, Song;Ma, Jing;Liu, Ninghao;Li, Jundong
• 通讯作者: Li, Jundong

Path-Specific Counterfactual Fairness for Recommender Systems

• DOI: 10.1145/3580305.3599462
• 发表时间: 2023-06
• 期刊: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Yaochen Zhu;Jing Ma;Liang Wu;Qilnli Guo;Liang Hong;Jundong Li

RELIANT: Fair Knowledge Distillation for Graph Neural Networks

• DOI: 10.48550/arxiv.2301.01150
• 发表时间: 2023-01
• 作者: Yushun Dong;Binchi Zhang;Yiling Yuan;Na Zou;Qi Wang;Jundong Li